tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-13 11:57:43 -04:00
Code Issues Packages Projects Releases Wiki Activity

ci : check that pre-tokenizer hashes are up-to-date (#15032)

Browse Source 
* torch is not required for convert_hf_to_gguf_update

* add --check-missing parameter

* check that pre-tokenizer hashes are up-to-date
This commit is contained in:
Sigbjørn Skjæret
2025-08-02 14:39:01 +02:00
committed by GitHub
parent 711d5e6fe6
commit 2bf3fbf0b5
3 changed files with 60 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

21
convert_hf_to_gguf_update.py
View File

@@ -59,6 +59,10 @@ parser.add_argument(
"--full", action="store_true",
help="download full list of models - make sure you have access to all of them",
)
parser.add_argument(
"--check-missing", action="store_true",
help="only check for missing pre-tokenizer hashes",
)
parser.add_argument(
"hf_token",
help="optional HF token",
@@ -70,6 +74,10 @@ hf_token = args.hf_token if args.hf_token is not None else hf_token
if hf_token is None:
logger.warning("HF token not found. You can provide it as an argument or set it in ~/.cache/huggingface/token")
if args.check_missing and args.full:
logger.warning("Downloading full list of models requested, ignoring --check-missing!")
args.check_missing = False
# TODO: this string has to exercise as much pre-tokenizer functionality as possible
# will be updated with time - contributions welcome
CHK_TXT = '\n \n\n \n\n\n \t \t\t \t\n \n \n \n \n🚀 (normal) 😶‍🌫️ (multiple emojis concatenated) ✅ 🦙🦙 3 33 333 3333 33333 333333 3333333 33333333 3.3 3..3 3...3 កាន់តែពិសេសអាច😁 ?我想在apple工作1314151天～ ------======= нещо на Български \'\'\'\'\'\'```````\"\"\"\"......!!!!!!?????? I\'ve been \'told he\'s there, \'RE you sure? \'M not sure I\'ll make it, \'D you like some tea? We\'Ve a\'lL'
@@ -222,12 +230,13 @@ if not args.full:
all_models = models.copy()
models = [model for model in all_models if model["name"] not in existing_models]
logging.info(f"Downloading {len(models)} models...")
for model in models:
try:
download_model(model)
except Exception as e:
logger.error(f"Failed to download model {model['name']}. Error: {e}")
if not args.check_missing:
logging.info(f"Downloading {len(models)} models...")
for model in models:
try:
download_model(model)
except Exception as e:
logger.error(f"Failed to download model {model['name']}. Error: {e}")
# generate the source code for the convert_hf_to_gguf.py:get_vocab_base_pre() function: